Jurnal Infotel (Sekolah Tinggi Teknologi Telematika Telkom Purwokerto)
Not a member yet
392 research outputs found
Sort by
All-in-one computation vs computational-offloading approaches: a performance evaluation of object detection strategies on android mobile devices
Full text linkObject detection gives a computer ability to classify objects in an image or video. However, high specified devices are needed to get a good performance. To enable devices with low specifications performs better, one way is offloading the computation process from a device with a low specification to another device with better specifications. This paper investigates the performance of object detection strategies on all-in-one Android mobile phone computation versus Android mobile phone computation with computational offloading on Nvidia Jetson Nano. The experiment carries out the video surveillance from the Android mobile phone with two scenarios, all-in-one object detection computation in a single Android device and decoupled object detection computation between an Android device and an Nvidia Jetson Nano. Android applications send video input for object detection using RTSP/RTMP streaming protocol and received by Nvidia Jetson Nano which acts as an RTSP/RTMP server. Then, the output of object detection is sent back to the Android device for being displayed to the user. The results show that the android device Huawei Y7 Pro with an average FPS performance of 1.82 and an average computing speed of 552 ms significantly improves when working with the Nvidia Jetson Nano, the average FPS becomes ten and the average computing speed becomes 95 ms. It means decoupling object detection computation between an Android device and an Nvidia Jetson Nano using the system provided in this paper successfully improves the detection speed performance
Designing a microcontroller-based half-duplex interface device drove by the touch-tone signal
Full text linkThe interface device for communicating (IDC) as a bridge for the merger between two different systems based on different protocols and standards can be made of several electronic modules. The two Arduino boards (UNO R3 and MEGA2560 R3) have been constructed as the electronic modules of a gateway become a haft-duplex IDC, and are driven by the touch-tone signal. The research objectives, i.e., assembling some of the hardware for the embodiment of the adapter system, making a program structure, and performing a test of the IDC system. The haft-duplex IDC has been carried out by integrating all components by wiring to form an embedded system. Then, programming the microcontroller modules based on the Arduino software is carried outin six stages. Finally, the simulation test with the provision of conditions is carried out and obtained of six conditions for (i) the circuit of ring detection, (ii) the circuit of voice-operated transmit, (iii) the circuit off/on the hook of the telephone module, (iv) the circuit of tone decoder, (v) dial-up telephone numbers via push buttons and switching IC circuits, and (vi) the circuits of voice recording and storage in the form to playback. The test's success with six conditions has been an indication that the microcontroller-based IDC system is functioning as expected. Completing, the conclusion, and recommendationsrelated to measurement on the various purposes and the real conditions for the half-duplex interface adapter can be implemented.The interface device for communicating (IDC) as a bridge for the merger between two different systems based on different protocols and standards can be made of several electronic modules. The two Arduino boards (UNO R3 and MEGA2560 R3) have been constructed as the electronic modules of a gateway become a haft-duplex IDC, and are driven by the touch-tone signal. The research objectives, i.e., assembling some of the hardware for the embodiment of the adapter system, making a program structure, and performing a test of the IDC system. The haft-duplex IDC has been carried out by integrating all components by wiring to form an embedded system. Then, programming the microcontroller modules based on the Arduino software is carried outin six stages. Finally, the simulation test with the provision of conditions is carried out and obtained of six conditions for (i) the circuit of ring detection, (ii) the circuit of voice-operated transmit, (iii) the circuit off/on the hook of the telephone module, (iv) the circuit of tone decoder, (v) dial-up telephone numbers via push buttons and switching IC circuits, and (vi) the circuits of voice recording and storage in the form to playback. The test's success with six conditions has been an indication that the microcontroller-based IDC system is functioning as expected. Completing, the conclusion, and recommendationsrelated to measurement on the various purposes and the real conditions for the half-duplex interface adapter can be implemented
Early Detection of Deforestation through Satellite Land Geospatial Images based on CNN Architecture
Full text linkThis study has developed a CNN model applied to classify the eight classes of land cover through satellite images. Early detection of deforestation has become one of the study’s objectives. Deforestation is the process of reducing natural forests for logging or converting forest land to non-forest land. The study considered two training models, a simple four hidden layer CNN compare with Alexnet architecture. The training variables such as input size, epoch, batch size, and learning rate were also investigated in this research. The Alexnet architecture produces validation accuracy over 100 epochs of 90.23% with a loss of 0.56. The best performance of the validation process with four hidden layers CNN got 95.2% accuracy and a loss of 0.17. This performance is achieved when the four hidden layer model is designed with an input size of 64 × 64, epoch 100, batch size 32, and learning rate of 0.001. It is expected that this land cover identification system can assist relevant authorities in the early detection of deforestation.This study has developed a CNN model applied to classify the eight classes of land cover through satellite images. Early detection of deforestation has become one of the study’s objectives. Deforestation is the process of reducing natural forests for logging or converting forest land to non-forest land. The study considered two training models, a simple four hidden layer CNN compare with Alexnet architecture. The training variables such as input size, epoch, batch size, and learning rate were also investigated in this research. The Alexnet architecture produces validation accuracy over 100 epochs of 90.23% with a loss of 0.56. The best performance of the validation process with four hidden layers CNN got 95.2% accuracy and a loss of 0.17. This performance is achieved when the four hidden layer model is designed with an input size of 64 × 64, epoch 100, batch size 32, and learning rate of 0.001. It is expected that this land cover identification system can assist relevant authorities in the early detection of deforestation
Design and Implementation of Smart Parking System Using Location-Based Service and Gamification Based On Internet Of Things
Full text linkInformation on the number of available parking slot capacity and trip routes to the destination parking area, and motivation in choosing a parking area location are parameters that can help two-wheeled vehicle users choose the right parking area location. The three parameters that determine the accuracy of selecting a parking area location are implemented in an Internet of Things (IoT) based smart parking system. This system can provide information about the maximum number of slot capacities and the number of available slot capacities at the parking area. Two-wheeled riders are given information about which route to take to the destination parking area by utilizing the Location-Based Service (LBS). These two features are then supported by applying the gamification method to motivate two-wheeled riders to choose the right parking area. The smart parking system is tested with considered Quality of Service (QoS) parameter and black box testing. The results of testing the smart parking system produce QoS performance on the Line of Sight (LOS) test, with an average delay is 71.66 ms, average jitter is 107.59 ms, and throughput is 23 kbps. Meanwhile, in the non-LOS test, the average delay is 132.88 ms, the average jitter is 200.84 ms, and the throughput is 12 kbps. Overall system performance obtained the percentage of reliability is 99.65 %, and availability is 99.65 %. In black-box testing, LBS and gamification methods can implement according to application requirements specifications.Information on the number of available parking slot capacity and trip routes to the destination parking area, and motivation in choosing a parking area location are parameters that can help two-wheeled vehicle users choose the right parking area location. The three parameters that determine the accuracy of selecting a parking area location are implemented in an Internet of Things (IoT) based smart parking system. This system can provide information about the maximum number of slot capacities and the number of available slot capacities at the parking area. Two-wheeled riders are given information about which route to take to the destination parking area by utilizing the Location-Based Service (LBS). These two features are then supported by applying the gamification method to motivate two-wheeled riders to choose the right parking area. The smart parking system is tested with considered Quality of Service (QoS) parameter and black box testing. The results of testing the smart parking system produce QoS performance on the Line of Sight (LOS) test, with an average delay is 71.66 ms, average jitter is 107.59 ms, and throughput is 23 kbps. Meanwhile, in the non-LOS test, the average delay is 132.88 ms, the average jitter is 200.84 ms, and the throughput is 12 kbps. Overall system performance obtained the percentage of reliability is 99.65 %, and availability is 99.65 %. In black-box testing, LBS and gamification methods can implement according to application requirements specifications
A New Method of Artificial to Solve the Optimization Problems without the Violated Constraints
Full text linkThere are some problems in optimization that cannot be derived mathematically. Various methods have been developed to solve the optimization problem with various functional forms, whether differentiated or not, to overcome the problem, which are known as artificial methods such as artificial neural networks, particle swarm optimization, and genetic algorithms. In the literature, it is said that there is an artificial method that frequently falls to the minimum local solution. The local minimum results are proof that the artificial method is not accurate. This paper proposes the Large to Small Area Technique for power system optimization, which works based on reducing feasible areas. This method can work accurately, which that never violates all constraints in reaching the optimal point. However, to conclude that this method is superior to others, logical arguments and tests with mathematical simulations are needed. This proposed method has been tested with 24 target points using ten functions consisting of a quadratic function and a first-order function. The results showed that this method has an average accuracy of 99.97% and an average computation time of 62 seconds. The proposed technique can be an alternative in solving the economic dispatch problem in the power system.There are some problems in optimization that cannot be derived mathematically. Various methods have been developed to solve the optimization problem with various functional forms, whether differentiated or not, to overcome the problem, which are known as artificial methods such as artificial neural networks, particle swarm optimization, and genetic algorithms. In the literature, it is said that there is an artificial method that frequently falls to the minimum local solution. The local minimum results are proof that the artificial method is not accurate. This paper proposes the Large to Small Area Technique for power system optimization, which works based on reducing feasible areas. This method can work accurately, which that never violates all constraints in reaching the optimal point. However, to conclude that this method is superior to others, logical arguments and tests with mathematical simulations are needed. This proposed method has been tested with 24 target points using ten functions consisting of a quadratic function and a first-order function. The results showed that this method has an average accuracy of 99.97% and an average computation time of 62 seconds. The proposed technique can be an alternative in solving the economic dispatch problem in the power system
Optimization of software defects prediction in imbalanced class using a combination of resampling methods with support vector machine and logistic regression
Full text linkThe main problem in producing high accuracy software defect prediction is if the data set has an imbalance class and dichotomous characteristics. The imbalanced class problem can be solved using a data level approach, such as resampling methods. While the problem of software defects predicting if the data set has dichotomous characteristics can be approached using the classification method. This study aimed to analyze the performance of the proposed software defect prediction method to identify the best combination of resampling methods with the appropriate classification method to provide the highest accuracy. The combination of the proposed methods first is the resampling process using oversampling, under-sampling, or hybrid methods. The second process uses the classification method, namely the Support Vector Machine (SVM) algorithm and the Logistic Regression (LR) algorithm. The proposed, tested model uses five NASA MDP data sets with the same number attributes of 37. Based on the t-test, the < = 0.0344 < 0.05 and the > = 3.1524 > 2.7765 which indicates that the combination of the proposed methods is suitable for classifying imbalanced class. The performance of the classification algorithm has also improved with the use of the resampling process. The average increase in AUC values using the resampling in the SVM algorithm is 17.19%, and the LR algorithm is at 7.26% compared to without the resampling process. Combining the three resampling methods with the SVM algorithm and the LR algorithm shows that the best combining method is the oversampling method with the SVM algorithm to software defects prediction in imbalanced class with an average accuracy value of 84.02% and AUC 91.65%.The main problem in producing high accuracy software defect prediction is if the data set has an imbalance class and dichotomous characteristics. The imbalanced class problem can be solved using a data level approach, such as resampling methods. While the problem of software defects predicting if the data set has dichotomous characteristics can be approached using the classification method. This study aimed to analyze the performance of the proposed software defect prediction method to identify the best combination of resampling methods with the appropriate classification method to provide the highest accuracy. The combination of the proposed methods first is the resampling process using oversampling, under-sampling, or hybrid methods. The second process uses the classification method, namely the Support Vector Machine (SVM) algorithm and the Logistic Regression (LR) algorithm. The proposed, tested model uses five NASA MDP data sets with the same number attributes of 37. Based on the t-test, the < = 0.0344 < 0.05 and the > = 3.1524 > 2.7765 which indicates that the combination of the proposed methods is suitable for classifying imbalanced class. The performance of the classification algorithm has also improved with the use of the resampling process. The average increase in AUC values using the resampling in the SVM algorithm is 17.19%, and the LR algorithm is at 7.26% compared to without the resampling process. Combining the three resampling methods with the SVM algorithm and the LR algorithm shows that the best combining method is the oversampling method with the SVM algorithm to software defects prediction in imbalanced class with an average accuracy value of 84.02% and AUC 91.65%
Telemetering Hasil Pengukuran Curah Hujan Menggunakan Transmisi Nirkabel 433 MHz
No full textThe line of sight (LOS) microwave communication system, especially those operating at frequencies above 10 GHz, is very susceptible to rain attenuation, particularly in tropical countries such as Indonesia. Therefore, it is essential to calculate rain attenuation estimation values as a basis for consideration in designing a line of sight microwave communication system to get stable communication. In this study, telemetering was designed to measure the rainfall intensity from a rain gauge device through a 433 MHz wireless transceiver. Measurement of rainfall intensity values via an Arduino-controlled rain gauge was transmitted directly to the monitoring room, which then processed to be displayed in graphical form in real time and can also be stored as data loggers. The rainfall telemetering device users can measure rainfall remotely and without having to wait for the rain like the rainfall manual measurement.Sistem komunikasi gelombang mikro line of sight (LOS), terutama yang beroperasi pada frekuensi di atas 10 GHz, sangat rentan terhadap redaman hujan, terutama di negara tropis seperti Indonesia. Oleh karena itu, perlu dilakukan perhitungan nilai estimasi redaman hujan sebagai dasar pertimbangan dalam merancang sistem komunikasi gelombang mikro line of sight untuk mendapatkan komunikasi yang stabil. Dalam penelitian ini sistem telemetering dirancang untuk mengukur intensitas curah hujan dari alat pengukur hujan melalui wireless transceiver 433 MHz. Pengukuran nilai intensitas curah hujan melalui alat pengukur hujan yang dikontrol Arduino dikirim langsung ke ruang pemantauan, yang kemudian diolah untuk ditampilkan dalam bentuk grafik secara real time dan juga dapat disimpan sebagai data logger. Pengguna dapat mengukur curah hujan dari jarak jauh dan tanpa harus menunggu hujan seperti pengukuran manual curah hujan
Planning of Indoor Femtocell Network for LTE 2300 MHz on Railways Carriages Using Radiowave Propagation Simulator 5.4
Full text linkThe indoor communication system is a system to solve the problem of weak signals received by placing a Femtocell Access Point (FAP) indoor area. The design of an indoor cellular communication network system is carried out using the Radiowave Propagation Simulator 5.4. The parameters observed were Received Signal Level (RSL) and Signal to Interface Ratio (SIR). The case study is the passenger carriage of the executive, business and economy passenger class. The research includes link budget calculations based on coverage and capacity by considering the type of train carriage material and train passenger capacity. The calculation results based on capacity obtained 1 FAP for executive and business class train passenger cars, while economy class train passenger cars obtained 2 FAP. The best scenario for executive class namely scenario 1A, the receiver gets average RSL of approximately -32.26 dBm and SIR of 0 dB. The best scenario for business class namely scenario 2A, the receiver gets average RSL of approximately -32.57 dBm and SIR of 0 dB. The best scenario for economy class namely scenario 3A, the receiver gets average RSL of approximately -29.80 dBm and the receiver gets average SIR of approximately 6.97 dBThe indoor communication system is a system to solve the problem of weak signals received by placing a Femtocell Access Point (FAP) indoor area. The design of an indoor cellular communication network system is carried out using the Radiowave Propagation Simulator 5.4. The parameters observed were Received Signal Level (RSL) and Signal to Interface Ratio (SIR). The case study is the passenger carriage of the executive, business and economy passenger class. The research includes link budget calculations based on coverage and capacity by considering the type of train carriage material and train passenger capacity. The calculation results based on capacity obtained 1 FAP for executive and business class train passenger cars, while economy class train passenger cars obtained 2 FAP. The best scenario for executive class namely scenario 1A, the receiver gets average RSL of approximately -32.26 dBm and SIR of 0 dB. The best scenario for business class namely scenario 2A, the receiver gets average RSL of approximately -32.57 dBm and SIR of 0 dB. The best scenario for economy class namely scenario 3A, the receiver gets average RSL of approximately -29.80 dBm and the receiver gets average SIR of approximately 6.97 d
Fuzzy based sensorless tracking controller on the dual-axis PV panel for optimizing the power production
Full text linkIn general active sun trackers move because they respond to light sensors that measure the intensity of sunlight. However, sensor-based trackers are usually more expensive than sensor-less trackers. In addition, based on several studies, a comparison between the sensor and sensorless based tracker only reports lower tracking error and higher power generation for sensor-based than sensorless tracker. However, it does not include an analysis of energy use on the sensor. Therefore, this study aims to design a sensorless closed-loop tracking system for solar panels with two degrees of freedom. The tracking controller in this study is based on the Fuzzy Logic Controller (FLC) method. In this study, a dual-axis PV can increase power output by 20.2% compared to a fixed PV (0 ° axis position). In comparison to a fixed PV, dual-axis PV adjusts the solar panel perpendicular to the sun's position to optimize electrical conversion.In general active sun trackers move because they respond to light sensors that measure the intensity of sunlight. However, sensor-based trackers are usually more expensive than sensor-less trackers. In addition, based on several studies, a comparison between the sensor and sensorless based tracker only reports lower tracking error and higher power generation for sensor-based than sensorless tracker. However, it does not include an analysis of energy use on the sensor. Therefore, this study aims to design a sensorless closed-loop tracking system for solar panels with two degrees of freedom. The tracking controller in this study is based on the Fuzzy Logic Controller (FLC) method. In this study, a dual-axis PV can increase power output by 20.2% compared to a fixed PV (0 ° axis position). In comparison to a fixed PV, dual-axis PV adjusts the solar panel perpendicular to the sun's position to optimize electrical conversion